Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image retrieval apparatus and image retrieving method

a technology of image retrieval and image, applied in the field of image retrieval apparatus, can solve the problems of inability to compare images having different coefficients and feature vectors, complicated apparatus, and high manufacturing cos

Inactive Publication Date: 2007-06-26
NEC CORP
View PDF18 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0013]A first object of the present invention is to solve the above mentioned problems of the conventional technology, and to provide an image retrieval apparatus, an image retrieving method, and an image retrieving program for realizing with a simple configuration of an apparatus the comparison and retrieval of each image in a system in which image feature vectors having various device configurations exist.

Problems solved by technology

Therefore, such a problem arises that the apparatus is complicated and costly for manufacturing.
However, in this case, since the dimension of the computed similarity depends on each image, the comparison cannot be carried out by using the same similarity.
That is, the comparison cannot be carried out on images having different coefficients and feature vectors.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image retrieval apparatus and image retrieving method
  • Image retrieval apparatus and image retrieving method
  • Image retrieval apparatus and image retrieving method

Examples

Experimental program
Comparison scheme
Effect test

embodiments

[0101]Next, a description will be made on embodiments of the present invention.

first embodiment

[0102]A first embodiment of the present invention is provided with a keyboard and a mouse as an input device, a personal computer as an image retrieval apparatus, a magnetic disk storage device as a storage device, and a display as an output device.

[0103]The personal computer comprises first image feature vector generation means, first image feature vector conversion means, second image feature vector conversion means, image feature vector similarity computation means, and a central processing unit as a similarity evaluation unit. In addition the magnetic disk storage device stores an image feature vector and configuration information for an image.

[0104]In this embodiment, the frequency distribution feature vector of an image is used as an example of an image feature vector. A generating method of the frequency distribution feature vector of a image is used as follows. That is, an image is divided into 8×8 blocks, and an average color of each block is computed, and a reduced image o...

second embodiment

[0112]Described below will be a second embodiment of the present invention.

[0113]The present embodiment has the same configuration as the first embodiment, but the central processing unit of a personal computer can also function, unlike the first embodiment, as means of interpolating an appropriate coefficient into an image feature vector of a query image or an images to be retrieved.

[0114]In a system in which still pictures and moving pictures coexist, it is assumed that a frame (image) extracted from moving pictures and still pictures have a frequency distribution feature vector having a total of 12 coefficients including 6 coefficients for a luminance signal and 3 coefficients for each chrominance signal. The configuration information describing the frequency distribution feature vector and the configuration information (example: a total of 12 coefficients including 6 coefficients for a luminance signal and 3 coefficients for each chrominance signal) of the frequency distribution...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An object of the present invention is to provide an image retrieval system for computing similarity in the case when components are different between an image feature vector of a query image and the image feature vectors of images to be retrieved when retrieval is carried out by using features of images. A first image feature vector conversion device converts a query image feature vector into a first image feature vector for use in a similarity computation according to similarity computation image feature vector configuration information describing a given configuration of an image feature vector for use in a similarity computation. A second image feature vector conversion device converts an images-to-be-retrieved feature vector into a second image feature vector for use in a similarity computation according to the similarity computation image feature vector configuration information. The image feature vector similarity computation devices compare the first image feature vector with the second image feature vector according to the similarity computation image feature vector configuration information, and compute the similarity.

Description

BACKGROUND OF THE INVENTION[0001]1. Field of the Invention[0002]The present invention relates to an image retrieval apparatus and a method for determining the similarity of each image, and retrieving an image similar to a specified image, and more specifically to an image retrieval system for computing the similarity when the configurations of the feature vector of a query image and the feature vector of an image to be compared are different from each other especially when a retrieving process is performed by using an image feature.[0003]2. Description of the Related Art[0004]Conventionally, an image retrieving process has been performed by converting the feature of an image into data, indicating an image feature vector, determining the similarity of each image by using the image feature vector, and retrieving a similar image (for example, from accumulated images). Various apparatuses and computer programs have been developed to perform the process.[0005]In the above mentioned conve...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/54G06K9/60G06T1/00G06F17/30G06T7/00G06T7/40
CPCG06F17/30247G06F17/30271G06F16/56G06F16/583
Inventor KASUTANI, EIJI
Owner NEC CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com